© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 11685
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to time or duration

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "during his time," referring to the duration of someone's tenure or period of activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesday
    -0.68
    reme
    -0.68
    ateg
    -0.67
    ishable
    -0.67
    versely
    -0.65
    ebted
    -0.62
    zsche
    -0.62
    ivably
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    vable
    -0.61
    POSITIVE LOGITS
    boarding
    0.90
     tenure
    0.89
     captivity
    0.85
     captive
    0.79
     abroad
    0.78
     overseas
    0.77
     touring
    0.73
     membership
    0.68
     composing
    0.68
     mistress
    0.68
    Activations Density 0.158%

    No Known Activations